Recent Advances in Deep Learning (AI602, Spring 2021)

Deep learning is a new area of machine learning research, which have demonstrated states-of-the-art performance on many artificial intelligence tasks, e.g., computer vision, speech recognition and natural language processing. In this lecture, I will cover some of recent advances (made mostly in the last 5 years) in this area.

Announcement

  • The maximum number of course registrations is around 40, and we cannot accept more now (do not send an email to Instructor or TA).

  • Office hours: TBA

Schedule

  • Lecture 0: Introduction to AI602

  • Lecture 1: Advanced optimizers for neural networks

  • Lecture 2: Advanced deep spatial models (e.g., for image recognition)

  • Lecture 3: Advanced deep temporal models (e.g., for language modeling)

  • Lecture 4: Paper presentation for Lecture 1

  • Lecture 5: Advanced deep generative models I (e.g., for image generation)

  • Lecture 6: Paper presentation for Lecture 2

  • Lecture 7: Advanced deep generative models II (e.g., for density estimation)

  • Lecture 8: Paper presentation for Lecture 3

  • Lecture 9: Novelty and uncertainty estimation

  • Lecture 10: Paper presentation for Lecture 5

  • Lecture 11: Unsupervised and self-supervised representation learning

  • Lecture 12: Paper presentation for Lecture 7

  • Lecture 13: Transfer and continual learning

  • Lecture 14: Paper presentation for Lecture 9

  • Lecture 15: Few-shot learning

  • Lecture 16: Paper presentation for Lecture 11

  • Lecture 17: Network_compression

  • Lecture 18: Paper presentation for Lecture 13

  • Lecture 19: Adversarial robustness

  • Lecture 20: Paper presentation for Lecture 15

  • Lecture 21: Interpretable and explainable learning

  • Lecture 22: Paper presentation for Lecture 17

  • Lecture 23: Paper presentation for Lecture 19

  • Lecture 24: Paper presentation for Lecture 21

Contact

Instructor: Jinwoo Shin (jinwoos@kaist.ac.kr)
TAs: TB